@article{BayerPruckner2023, author = {Bayer, Daniel and Pruckner, Marco}, title = {A digital twin of a local energy system based on real smart meter data}, series = {Energy Informatics}, volume = {6}, journal = {Energy Informatics}, doi = {10.1186/s42162-023-00263-6}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-357456}, year = {2023}, abstract = {The steadily increasing usage of smart meters generates a valuable amount of high-resolution data about the individual energy consumption and production of local energy systems. Private households install more and more photovoltaic systems, battery storage and big consumers like heat pumps. Thus, our vision is to augment these collected smart meter time series of a complete system (e.g., a city, town or complex institutions like airports) with simulatively added previously named components. We, therefore, propose a novel digital twin of such an energy system based solely on a complete set of smart meter data including additional building data. Based on the additional geospatial data, the twin is intended to represent the addition of the abovementioned components as realistically as possible. Outputs of the twin can be used as a decision support for either system operators where to strengthen the system or for individual households where and how to install photovoltaic systems and batteries. Meanwhile, the first local energy system operators had such smart meter data of almost all residential consumers for several years. We acquire those of an exemplary operator and discuss a case study presenting some features of our digital twin and highlighting the value of the combination of smart meter and geospatial data.}, language = {en} } @article{FischerHarteltPuppe2023, author = {Fischer, Norbert and Hartelt, Alexander and Puppe, Frank}, title = {Line-level layout recognition of historical documents with background knowledge}, series = {Algorithms}, volume = {16}, journal = {Algorithms}, number = {3}, issn = {1999-4893}, doi = {10.3390/a16030136}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310938}, year = {2023}, abstract = {Digitization and transcription of historic documents offer new research opportunities for humanists and are the topics of many edition projects. However, manual work is still required for the main phases of layout recognition and the subsequent optical character recognition (OCR) of early printed documents. This paper describes and evaluates how deep learning approaches recognize text lines and can be extended to layout recognition using background knowledge. The evaluation was performed on five corpora of early prints from the 15th and 16th Centuries, representing a variety of layout features. While the main text with standard layouts could be recognized in the correct reading order with a precision and recall of up to 99.9\%, also complex layouts were recognized at a rate as high as 90\% by using background knowledge, the full potential of which was revealed if many pages of the same source were transcribed.}, language = {en} } @article{GreubelAndresHennecke2023, author = {Greubel, Andr{\´e} and Andres, Daniela and Hennecke, Martin}, title = {Analyzing reporting on ransomware incidents: a case study}, series = {Social Sciences}, volume = {12}, journal = {Social Sciences}, number = {5}, issn = {2076-0760}, doi = {10.3390/socsci12050265}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-313746}, year = {2023}, abstract = {Knowledge about ransomware is important for protecting sensitive data and for participating in public debates about suitable regulation regarding its security. However, as of now, this topic has received little to no attention in most school curricula. As such, it is desirable to analyze what citizens can learn about this topic outside of formal education, e.g., from news articles. This analysis is both relevant to analyzing the public discourse about ransomware, as well as to identify what aspects of this topic should be included in the limited time available for this topic in formal education. Thus, this paper was motivated both by educational and media research. The central goal is to explore how the media reports on this topic and, additionally, to identify potential misconceptions that could stem from this reporting. To do so, we conducted an exploratory case study into the reporting of 109 media articles regarding a high-impact ransomware event: the shutdown of the Colonial Pipeline (located in the east of the USA). We analyzed how the articles introduced central terminology, what details were provided, what details were not, and what (mis-)conceptions readers might receive from them. Our results show that an introduction of the terminology and technical concepts of security is insufficient for a complete understanding of the incident. Most importantly, the articles may lead to four misconceptions about ransomware that are likely to lead to misleading conclusions about the responsibility for the incident and possible political and technical options to prevent such attacks in the future.}, language = {en} } @article{HossfeldHeegaardKellerer2023, author = {Hossfeld, Tobias and Heegaard, Poul E. and Kellerer, Wolfgang}, title = {Comparing the scalability of communication networks and systems}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, doi = {10.1109/ACCESS.2023.3314201}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349403}, pages = {101474-101497}, year = {2023}, abstract = {Scalability is often mentioned in literature, but a stringent definition is missing. In particular, there is no general scalability assessment which clearly indicates whether a system scales or not or whether a system scales better than another. The key contribution of this article is the definition of a scalability index (SI) which quantifies if a system scales in comparison to another system, a hypothetical system, e.g., linear system, or the theoretically optimal system. The suggested SI generalizes different metrics from literature, which are specialized cases of our SI. The primary target of our scalability framework is, however, benchmarking of two systems, which does not require any reference system. The SI is demonstrated and evaluated for different use cases, that are (1) the performance of an IoT load balancer depending on the system load, (2) the availability of a communication system depending on the size and structure of the network, (3) scalability comparison of different location selection mechanisms in fog computing with respect to delays and energy consumption; (4) comparison of time-sensitive networking (TSN) mechanisms in terms of efficiency and utilization. Finally, we discuss how to use and how not to use the SI and give recommendations and guidelines in practice. To the best of our knowledge, this is the first work which provides a general SI for the comparison and benchmarking of systems, which is the primary target of our scalability analysis.}, language = {en} } @article{KempfKrugPuppe2023, author = {Kempf, Sebastian and Krug, Markus and Puppe, Frank}, title = {KIETA: Key-insight extraction from scientific tables}, series = {Applied Intelligence}, volume = {53}, journal = {Applied Intelligence}, number = {8}, issn = {0924-669X}, doi = {10.1007/s10489-022-03957-8}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-324180}, pages = {9513-9530}, year = {2023}, abstract = {An important but very time consuming part of the research process is literature review. An already large and nevertheless growing ground set of publications as well as a steadily increasing publication rate continue to worsen the situation. Consequently, automating this task as far as possible is desirable. Experimental results of systems are key-insights of high importance during literature review and usually represented in form of tables. Our pipeline KIETA exploits these tables to contribute to the endeavor of automation by extracting them and their contained knowledge from scientific publications. The pipeline is split into multiple steps to guarantee modularity as well as analyzability, and agnosticim regarding the specific scientific domain up until the knowledge extraction step, which is based upon an ontology. Additionally, a dataset of corresponding articles has been manually annotated with information regarding table and knowledge extraction. Experiments show promising results that signal the possibility of an automated system, while also indicating limits of extracting knowledge from tables without any context.}, language = {en} } @article{KirikkayisGallikWinteretal.2023, author = {Kirikkayis, Yusuf and Gallik, Florian and Winter, Michael and Reichert, Manfred}, title = {BPMNE4IoT: a framework for modeling, executing and monitoring IoT-driven processes}, series = {Future Internet}, volume = {15}, journal = {Future Internet}, number = {3}, issn = {1999-5903}, doi = {10.3390/fi15030090}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-304097}, year = {2023}, abstract = {The Internet of Things (IoT) enables a variety of smart applications, including smart home, smart manufacturing, and smart city. By enhancing Business Process Management Systems with IoT capabilities, the execution and monitoring of business processes can be significantly improved. Providing a holistic support for modeling, executing and monitoring IoT-driven processes, however, constitutes a challenge. Existing process modeling and process execution languages, such as BPMN 2.0, are unable to fully meet the IoT characteristics (e.g., asynchronicity and parallelism) of IoT-driven processes. In this article, we present BPMNE4IoT—A holistic framework for modeling, executing and monitoring IoT-driven processes. We introduce various artifacts and events based on the BPMN 2.0 metamodel that allow realizing the desired IoT awareness of business processes. The framework is evaluated along two real-world scenarios from two different domains. Moreover, we present a user study for comparing BPMNE4IoT and BPMN 2.0. In particular, this study has confirmed that the BPMNE4IoT framework facilitates the support of IoT-driven processes.}, language = {en} } @article{LimanMayFetteetal.2023, author = {Liman, Leon and May, Bernd and Fette, Georg and Krebs, Jonathan and Puppe, Frank}, title = {Using a clinical data warehouse to calculate and present key metrics for the radiology department: implementation and performance evaluation}, series = {JMIR Medical Informatics}, volume = {11}, journal = {JMIR Medical Informatics}, issn = {2291-9694}, doi = {10.2196/41808}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349411}, year = {2023}, abstract = {Background: Due to the importance of radiologic examinations, such as X-rays or computed tomography scans, for many clinical diagnoses, the optimal use of the radiology department is 1 of the primary goals of many hospitals. Objective: This study aims to calculate the key metrics of this use by creating a radiology data warehouse solution, where data from radiology information systems (RISs) can be imported and then queried using a query language as well as a graphical user interface (GUI). Methods: Using a simple configuration file, the developed system allowed for the processing of radiology data exported from any kind of RIS into a Microsoft Excel, comma-separated value (CSV), or JavaScript Object Notation (JSON) file. These data were then imported into a clinical data warehouse. Additional values based on the radiology data were calculated during this import process by implementing 1 of several provided interfaces. Afterward, the query language and GUI of the data warehouse were used to configure and calculate reports on these data. For the most common types of requested reports, a web interface was created to view their numbers as graphics. Results: The tool was successfully tested with the data of 4 different German hospitals from 2018 to 2021, with a total of 1,436,111 examinations. The user feedback was good, since all their queries could be answered if the available data were sufficient. The initial processing of the radiology data for using them with the clinical data warehouse took (depending on the amount of data provided by each hospital) between 7 minutes and 1 hour 11 minutes. Calculating 3 reports of different complexities on the data of each hospital was possible in 1-3 seconds for reports with up to 200 individual calculations and in up to 1.5 minutes for reports with up to 8200 individual calculations. Conclusions: A system was developed with the main advantage of being generic concerning the export of different RISs as well as concerning the configuration of queries for various reports. The queries could be configured easily using the GUI of the data warehouse, and their results could be exported into the standard formats Excel and CSV for further processing.}, language = {en} } @article{MaiwaldBruschkeSchneideretal.2023, author = {Maiwald, Ferdinand and Bruschke, Jonas and Schneider, Danilo and Wacker, Markus and Niebling, Florian}, title = {Giving historical photographs a new perspective: introducing camera orientation parameters as new metadata in a large-scale 4D application}, series = {Remote Sensing}, volume = {15}, journal = {Remote Sensing}, number = {7}, issn = {2072-4292}, doi = {10.3390/rs15071879}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-311103}, year = {2023}, abstract = {The ongoing digitization of historical photographs in archives allows investigating the quality, quantity, and distribution of these images. However, the exact interior and exterior camera orientations of these photographs are usually lost during the digitization process. The proposed method uses content-based image retrieval (CBIR) to filter exterior images of single buildings in combination with metadata information. The retrieved photographs are automatically processed in an adapted structure-from-motion (SfM) pipeline to determine the camera parameters. In an interactive georeferencing process, the calculated camera positions are transferred into a global coordinate system. As all image and camera data are efficiently stored in the proposed 4D database, they can be conveniently accessed afterward to georeference newly digitized images by using photogrammetric triangulation and spatial resection. The results show that the CBIR and the subsequent SfM are robust methods for various kinds of buildings and different quantity of data. The absolute accuracy of the camera positions after georeferencing lies in the range of a few meters likely introduced by the inaccurate LOD2 models used for transformation. The proposed photogrammetric method, the database structure, and the 4D visualization interface enable adding historical urban photographs and 3D models from other locations.}, language = {en} } @article{MuellerLeppichGeissetal.2023, author = {M{\"u}ller, Konstantin and Leppich, Robert and Geiß, Christian and Borst, Vanessa and Pelizari, Patrick Aravena and Kounev, Samuel and Taubenb{\"o}ck, Hannes}, title = {Deep neural network regression for normalized digital surface model generation with Sentinel-2 imagery}, series = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, volume = {16}, journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, issn = {1939-1404}, doi = {10.1109/JSTARS.2023.3297710}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349424}, pages = {8508-8519}, year = {2023}, abstract = {In recent history, normalized digital surface models (nDSMs) have been constantly gaining importance as a means to solve large-scale geographic problems. High-resolution surface models are precious, as they can provide detailed information for a specific area. However, measurements with a high resolution are time consuming and costly. Only a few approaches exist to create high-resolution nDSMs for extensive areas. This article explores approaches to extract high-resolution nDSMs from low-resolution Sentinel-2 data, allowing us to derive large-scale models. We thereby utilize the advantages of Sentinel 2 being open access, having global coverage, and providing steady updates through a high repetition rate. Several deep learning models are trained to overcome the gap in producing high-resolution surface maps from low-resolution input data. With U-Net as a base architecture, we extend the capabilities of our model by integrating tailored multiscale encoders with differently sized kernels in the convolution as well as conformed self-attention inside the skip connection gates. Using pixelwise regression, our U-Net base models can achieve a mean height error of approximately 2 m. Moreover, through our enhancements to the model architecture, we reduce the model error by more than 7\%.}, language = {en} } @article{SeufertPoigneeSeufertetal.2023, author = {Seufert, Anika and Poign{\´e}e, Fabian and Seufert, Michael and Hoßfeld, Tobias}, title = {Share and multiply: modeling communication and generated traffic in private WhatsApp groups}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, doi = {10.1109/ACCESS.2023.3254913}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349430}, pages = {25401-25414}, year = {2023}, abstract = {Group-based communication is a highly popular communication paradigm, which is especially prominent in mobile instant messaging (MIM) applications, such as WhatsApp. Chat groups in MIM applications facilitate the sharing of various types of messages (e.g., text, voice, image, video) among a large number of participants. As each message has to be transmitted to every other member of the group, which multiplies the traffic, this has a massive impact on the underlying communication networks. However, most chat groups are private and network operators cannot obtain deep insights into MIM communication via network measurements due to end-to-end encryption. Thus, the generation of traffic is not well understood, given that it depends on sizes of communication groups, speed of communication, and exchanged message types. In this work, we provide a huge data set of 5,956 private WhatsApp chat histories, which contains over 76 million messages from more than 117,000 users. We describe and model the properties of chat groups and users, and the communication within these chat groups, which gives unprecedented insights into private MIM communication. In addition, we conduct exemplary measurements for the most popular message types, which empower the provided models to estimate the traffic over time in a chat group.}, language = {en} }